Instructions to use nvidia/difix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nvidia/difix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nvidia/difix", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Support has moved β HF Community will be disabled
#4
pinned
by fhofherr - opened
Support has moved
DiFix is a previous-generation model. Please use Fixer for active development and support.
We are turning off the Hugging Face Community tab on this model card. Please use these channels going forward:
- Usage questions β NVIDIA Developer Forum: https://forums.developer.nvidia.com/c/omniverse/platform/nurec/752
- Code bugs, documentation issues, and feature requests β Fixer GitHub: https://github.com/nv-tlabs/Fixer/issues/new/choose
- Security vulnerabilities β NVIDIA Vulnerability Disclosure Program: https://app.intigriti.com/programs/nvidia/nvidiavdp/detail
The model card README at the top of this page also lists these channels permanently.
Timeline: We will turn off the Community tab on 08/10/2026. If you have an open thread here, please continue it through the appropriate channel above.
Thanks!
fhofherr pinned discussion